Closed zhwa closed 3 years ago
Hi,
We currently don't support multiple hypothesis at the moment. Here is the code pointer for viterbi
- https://github.com/facebookresearch/gtn/blob/master/gtn/functions/shortest.cpp#L190 if you want to hack things to support...
It seems that in
model.viterbi(self, outputs)
, only one recognition results will be returned for each sample. Is it possible to return multiple alternates from this decoding method, like beam search? If yes, what would be the recommended decoding algorithm? Will that be time consuming?Thanks!